Análisis de modelos SOM - Frecuencia datos de entrada: dia

Modelo

• ID: 11
• Descripción:
• Frecuencia: dia
• Variables: fecha_cnt, tmax, tmin, precip, longitud, latitud, altitud
• Dimensiones del mapa: 10,10
• Iteraciones: 1000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-011.rds.xz")
summary(model)

SOM of size 10x10 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 1065343 objects.
Mean distance to the closest unit in the map: 0.603.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_dia_2k.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt          tmax       
 Length:1065343     Length:1065343     Min.   :  1.0   Min.   :-196.0  
 Class :character   Class :character   1st Qu.: 91.0   1st Qu.: 144.0  
 Mode  :character   Mode  :character   Median :183.0   Median : 201.0  
                                       Mean   :182.8   Mean   : 201.5  
                                       3rd Qu.:274.0   3rd Qu.: 263.0  
                                       Max.   :366.0   Max.   : 469.0  
      tmin             precip            nevada    prof_nieve       
 Min.   :-252.00   Min.   :   0.00   Min.   :0   Min.   :   0.0000  
 1st Qu.:  47.00   1st Qu.:   0.00   1st Qu.:0   1st Qu.:   0.0000  
 Median : 100.00   Median :   0.00   Median :0   Median :   0.0000  
 Mean   :  97.54   Mean   :  17.05   Mean   :0   Mean   :   0.6185  
 3rd Qu.: 153.00   3rd Qu.:   2.00   3rd Qu.:0   3rd Qu.:   0.0000  
 Max.   : 332.00   Max.   :3361.00   Max.   :0   Max.   :1240.0000  
    longitud        latitud           altitud    
 Min.   :27.82   Min.   :-17.889   Min.   :   1  
 1st Qu.:39.47   1st Qu.: -4.850   1st Qu.:  47  
 Median :41.29   Median : -1.411   Median : 287  
 Mean   :40.10   Mean   : -2.391   Mean   : 486  
 3rd Qu.:42.22   3rd Qu.:  1.296   3rd Qu.: 691  
 Max.   :43.57   Max.   :  4.216   Max.   :2535  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

    1     2     3     4     5     6     7     8     9    10    11    12    13 
13261 11494 18100 18351 18232 13049  8859  1649   672   133 11960 13624 11825 
   14    15    16    17    18    19    20    21    22    23    24    25    26 
11043 11893 17538 14312  5378  2199  1490 16415  7627 10189  6979  9174 11567 
   27    28    29    30    31    32    33    34    35    36    37    38    39 
12881  7659  4243  8730  7714  9946  6079 13700  9665 11359  9791  8748  2413 
   40    41    42    43    44    45    46    47    48    49    50    51    52 
10397 11331  6538 11510 11543 10201 10522 10850 14795  3186 12750 15990 15920 
   53    54    55    56    57    58    59    60    61    62    63    64    65 
 9085 13117  9269  7082  4695 12700 10074  6219 13647 14930 11258 10348  9904 
   66    67    68    69    70    71    72    73    74    75    76    77    78 
 5334 10274 10821  2924  9788 11300 13907 11738 20108 13165 10387  7309  9681 
   79    80    81    82    83    84    85    86    87    88    89    90    91 
 8863  9382 13283  6493 15768 13115 11962 15932 18982  7470  6912  6677  9351 
   92    93    94    95    96    97    98    99   100 
15568 23893 17335 19078  7695  9256  8050 15497 10243 

Comprobación de nodos vacíos:

dim_model <- 10*10;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "precip", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

     fecha_cnt       tmax       tmin     precip    longitud   latitud
[1,] 0.1283135 -0.6991573 -0.7457657  0.1941083  0.54821738 0.4429048
[2,] 0.6350321  0.3295530  0.3036102 -0.1590133 -0.01254259 0.1250637
         altitud
[1,]  0.50755497
[2,] -0.02289429

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   altitud   latitud fecha_cnt    precip      tmax      tmin 
0.9742736 0.9609069 0.9584478 0.9560576 0.9547634 0.9440945 0.9404333 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax           tmin             precip           nevada 
 Min.   :  1.0   Min.   :-196   Min.   :-252.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 91.0   1st Qu.: 145   1st Qu.:  47.00   1st Qu.:  0.00   1st Qu.:0  
 Median :183.0   Median : 202   Median : 100.00   Median :  0.00   Median :0  
 Mean   :182.7   Mean   : 202   Mean   :  97.68   Mean   : 13.04   Mean   :0  
 3rd Qu.:274.0   3rd Qu.: 263   3rd Qu.: 153.00   3rd Qu.:  1.00   3rd Qu.:0  
 Max.   :366.0   Max.   : 469   Max.   : 332.00   Max.   :357.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :   0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:   0.0000   1st Qu.:39.47   1st Qu.: -4.850   1st Qu.:  47.0  
 Median :   0.0000   Median :41.29   Median : -1.411   Median : 287.0  
 Mean   :   0.5938   Mean   :40.10   Mean   : -2.401   Mean   : 484.5  
 3rd Qu.:   0.0000   3rd Qu.:42.22   3rd Qu.:  1.296   3rd Qu.: 690.0  
 Max.   :1240.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax             tmin             precip      
 Min.   :  1.0   Min.   :-124.0   Min.   :-157.00   Min.   : 267.0  
 1st Qu.: 90.0   1st Qu.:  98.0   1st Qu.:  45.25   1st Qu.: 353.0  
 Median :217.0   Median : 144.0   Median :  91.00   Median : 415.0  
 Mean   :195.8   Mean   : 141.6   Mean   :  81.23   Mean   : 469.2  
 3rd Qu.:299.0   3rd Qu.: 191.0   3rd Qu.: 128.00   3rd Qu.: 530.0  
 Max.   :366.0   Max.   : 369.0   Max.   : 254.00   Max.   :1206.0  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :  0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0   1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -3.9876  
 Median :0   Median :  0.000   Median :41.96   Median :  0.7789  
 Mean   :0   Mean   :  3.432   Mean   :41.14   Mean   : -1.1966  
 3rd Qu.:0   3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.8375  
 Max.   :0   Max.   :899.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  61.0  
 Median : 287.0  
 Mean   : 659.1  
 3rd Qu.: 900.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip         nevada 
 Min.   : 21.0   Min.   :  7.0   Min.   :-41.0   Min.   :1208   Min.   :0  
 1st Qu.: 80.0   1st Qu.: 80.0   1st Qu.: 47.0   1st Qu.:1300   1st Qu.:0  
 Median :283.0   Median :133.0   Median :102.0   Median :1393   Median :0  
 Mean   :217.2   Mean   :139.1   Mean   : 92.8   Mean   :1518   Mean   :0  
 3rd Qu.:306.0   3rd Qu.:193.0   3rd Qu.:143.0   3rd Qu.:1598   3rd Qu.:0  
 Max.   :354.0   Max.   :282.0   Max.   :202.0   Max.   :3361   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:39.48   1st Qu.: -1.1692   1st Qu.:  43.0  
 Median :  0.000   Median :40.80   Median :  0.4914   Median : 261.0  
 Mean   :  8.256   Mean   :39.53   Mean   : -1.3609   Mean   : 622.9  
 3rd Qu.:  0.000   3rd Qu.:41.84   3rd Qu.:  1.7678   3rd Qu.:1055.0  
 Max.   :559.000   Max.   :43.57   Max.   :  3.0967   Max.   :2519.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax             tmin             precip      
 Min.   :  1.0   Min.   :-196.0   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 54.0   1st Qu.: 114.0   1st Qu.:  16.00   1st Qu.:  0.00  
 Median :111.0   Median : 152.0   Median :  54.00   Median :  0.00  
 Mean   :159.2   Mean   : 147.2   Mean   :  49.49   Mean   : 20.82  
 3rd Qu.:306.0   3rd Qu.: 186.0   3rd Qu.:  86.00   3rd Qu.: 10.00  
 Max.   :366.0   Max.   : 389.0   Max.   : 264.00   Max.   :357.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:40.41   1st Qu.: -4.010  
 Median :0   Median :   0.000   Median :41.59   Median : -1.229  
 Mean   :0   Mean   :   1.075   Mean   :41.06   Mean   : -1.562  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.38   3rd Qu.:  1.363  
 Max.   :0   Max.   :1240.000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  87.0  
 Median : 459.0  
 Mean   : 619.8  
 3rd Qu.: 873.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  1.0   Min.   :-32.0   Min.   :-75.0   Min.   :  0.000   Min.   :0  
 1st Qu.:168.0   1st Qu.:233.0   1st Qu.:127.0   1st Qu.:  0.000   1st Qu.:0  
 Median :215.0   Median :268.0   Median :158.0   Median :  0.000   Median :0  
 Mean   :211.3   Mean   :269.1   Mean   :156.6   Mean   :  3.523   Mean   :0  
 3rd Qu.:260.0   3rd Qu.:305.0   3rd Qu.:187.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :469.0   Max.   :332.0   Max.   :332.000   Max.   :0  
   prof_nieve           longitud        latitud           altitud    
 Min.   :   0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1  
 1st Qu.:   0.0000   1st Qu.:37.79   1st Qu.: -5.879   1st Qu.:  33  
 Median :   0.0000   Median :40.84   Median : -1.861   Median : 123  
 Mean   :   0.0054   Mean   :38.92   Mean   : -3.427   Mean   : 319  
 3rd Qu.:   0.0000   3rd Qu.:41.81   3rd Qu.:  1.179   3rd Qu.: 554  
 Max.   :1039.0000   Max.   :43.57   Max.   :  4.216   Max.   :2371  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip      
 Min.   :  1.0   Min.   :-124.0   Min.   :-157.00   Min.   : 267.0  
 1st Qu.: 90.0   1st Qu.:  98.0   1st Qu.:  45.25   1st Qu.: 353.0  
 Median :217.0   Median : 144.0   Median :  91.00   Median : 415.0  
 Mean   :195.8   Mean   : 141.6   Mean   :  81.23   Mean   : 469.2  
 3rd Qu.:299.0   3rd Qu.: 191.0   3rd Qu.: 128.00   3rd Qu.: 530.0  
 Max.   :366.0   Max.   : 369.0   Max.   : 254.00   Max.   :1206.0  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :  0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0   1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -3.9876  
 Median :0   Median :  0.000   Median :41.96   Median :  0.7789  
 Mean   :0   Mean   :  3.432   Mean   :41.14   Mean   : -1.1966  
 3rd Qu.:0   3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.8375  
 Max.   :0   Max.   :899.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  61.0  
 Median : 287.0  
 Mean   : 659.1  
 3rd Qu.: 900.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip         nevada 
 Min.   : 21.0   Min.   :  7.0   Min.   :-41.0   Min.   :1208   Min.   :0  
 1st Qu.: 80.0   1st Qu.: 80.0   1st Qu.: 47.0   1st Qu.:1300   1st Qu.:0  
 Median :283.0   Median :133.0   Median :102.0   Median :1393   Median :0  
 Mean   :217.2   Mean   :139.1   Mean   : 92.8   Mean   :1518   Mean   :0  
 3rd Qu.:306.0   3rd Qu.:193.0   3rd Qu.:143.0   3rd Qu.:1598   3rd Qu.:0  
 Max.   :354.0   Max.   :282.0   Max.   :202.0   Max.   :3361   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:39.48   1st Qu.: -1.1692   1st Qu.:  43.0  
 Median :  0.000   Median :40.80   Median :  0.4914   Median : 261.0  
 Mean   :  8.256   Mean   :39.53   Mean   : -1.3609   Mean   : 622.9  
 3rd Qu.:  0.000   3rd Qu.:41.84   3rd Qu.:  1.7678   3rd Qu.:1055.0  
 Max.   :559.000   Max.   :43.57   Max.   :  3.0967   Max.   :2519.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax             tmin             precip      
 Min.   :  1.0   Min.   :-196.0   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 54.0   1st Qu.: 114.0   1st Qu.:  16.00   1st Qu.:  0.00  
 Median :111.0   Median : 152.0   Median :  54.00   Median :  0.00  
 Mean   :159.2   Mean   : 147.2   Mean   :  49.49   Mean   : 20.82  
 3rd Qu.:306.0   3rd Qu.: 186.0   3rd Qu.:  86.00   3rd Qu.: 10.00  
 Max.   :366.0   Max.   : 389.0   Max.   : 264.00   Max.   :357.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:40.41   1st Qu.: -4.010  
 Median :0   Median :   0.000   Median :41.59   Median : -1.229  
 Mean   :0   Mean   :   1.075   Mean   :41.06   Mean   : -1.562  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.38   3rd Qu.:  1.363  
 Max.   :0   Max.   :1240.000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  87.0  
 Median : 459.0  
 Mean   : 619.8  
 3rd Qu.: 873.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  3.0   Min.   :128.0   Min.   : -4.0   Min.   :  0.000   Min.   :0  
 1st Qu.:175.0   1st Qu.:240.0   1st Qu.:126.0   1st Qu.:  0.000   1st Qu.:0  
 Median :217.0   Median :275.0   Median :155.0   Median :  0.000   Median :0  
 Mean   :216.1   Mean   :275.4   Mean   :155.4   Mean   :  3.373   Mean   :0  
 3rd Qu.:259.0   3rd Qu.:310.0   3rd Qu.:185.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :469.0   Max.   :332.0   Max.   :128.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :   0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:   0.0000   1st Qu.:39.47   1st Qu.:-4.049   1st Qu.:  42.0  
 Median :   0.0000   Median :41.17   Median :-0.482   Median : 158.0  
 Mean   :   0.0062   Mean   :40.57   Mean   :-1.439   Mean   : 308.7  
 3rd Qu.:   0.0000   3rd Qu.:41.98   3rd Qu.: 1.384   3rd Qu.: 554.0  
 Max.   :1039.0000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip      
 Min.   :  1.0   Min.   :-124.0   Min.   :-157.00   Min.   : 267.0  
 1st Qu.: 90.0   1st Qu.:  98.0   1st Qu.:  45.25   1st Qu.: 353.0  
 Median :217.0   Median : 144.0   Median :  91.00   Median : 415.0  
 Mean   :195.8   Mean   : 141.6   Mean   :  81.23   Mean   : 469.2  
 3rd Qu.:299.0   3rd Qu.: 191.0   3rd Qu.: 128.00   3rd Qu.: 530.0  
 Max.   :366.0   Max.   : 369.0   Max.   : 254.00   Max.   :1206.0  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :  0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0   1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -3.9876  
 Median :0   Median :  0.000   Median :41.96   Median :  0.7789  
 Mean   :0   Mean   :  3.432   Mean   :41.14   Mean   : -1.1966  
 3rd Qu.:0   3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.8375  
 Max.   :0   Max.   :899.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  61.0  
 Median : 287.0  
 Mean   : 659.1  
 3rd Qu.: 900.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip         nevada 
 Min.   : 21.0   Min.   :  7.0   Min.   :-41.0   Min.   :1208   Min.   :0  
 1st Qu.: 80.0   1st Qu.: 80.0   1st Qu.: 47.0   1st Qu.:1300   1st Qu.:0  
 Median :283.0   Median :133.0   Median :102.0   Median :1393   Median :0  
 Mean   :217.2   Mean   :139.1   Mean   : 92.8   Mean   :1518   Mean   :0  
 3rd Qu.:306.0   3rd Qu.:193.0   3rd Qu.:143.0   3rd Qu.:1598   3rd Qu.:0  
 Max.   :354.0   Max.   :282.0   Max.   :202.0   Max.   :3361   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:39.48   1st Qu.: -1.1692   1st Qu.:  43.0  
 Median :  0.000   Median :40.80   Median :  0.4914   Median : 261.0  
 Mean   :  8.256   Mean   :39.53   Mean   : -1.3609   Mean   : 622.9  
 3rd Qu.:  0.000   3rd Qu.:41.84   3rd Qu.:  1.7678   3rd Qu.:1055.0  
 Max.   :559.000   Max.   :43.57   Max.   :  3.0967   Max.   :2519.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  1.0   Min.   :-32.0   Min.   :-75.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:208.0   1st Qu.:145.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :229.1   Mean   :164.5   Mean   :  4.478   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429.0   Max.   :322.0   Max.   :332.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.06   Mean   : 384.3  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :  1.0   Min.   :-65.0   Min.   :-240.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 51.0   1st Qu.:122.0   1st Qu.:  22.00   1st Qu.:  0.00   1st Qu.:0  
 Median :104.0   Median :157.0   Median :  57.00   Median :  0.00   Median :0  
 Mean   :156.2   Mean   :155.1   Mean   :  53.92   Mean   : 20.59   Mean   :0  
 3rd Qu.:310.0   3rd Qu.:189.0   3rd Qu.:  87.00   3rd Qu.:  9.00   3rd Qu.:0  
 Max.   :366.0   Max.   :389.0   Max.   : 264.00   Max.   :357.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud    
 Min.   :   0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1  
 1st Qu.:   0.0000   1st Qu.:40.30   1st Qu.: -4.680   1st Qu.:  71  
 Median :   0.0000   Median :41.39   Median : -1.861   Median : 370  
 Mean   :   0.1084   Mean   :40.90   Mean   : -1.872   Mean   : 420  
 3rd Qu.:   0.0000   3rd Qu.:42.24   3rd Qu.:  1.168   3rd Qu.: 691  
 Max.   :1240.0000   Max.   :43.57   Max.   :  4.216   Max.   :1894  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  3.0   Min.   :128.0   Min.   : -4.0   Min.   :  0.000   Min.   :0  
 1st Qu.:175.0   1st Qu.:240.0   1st Qu.:126.0   1st Qu.:  0.000   1st Qu.:0  
 Median :217.0   Median :275.0   Median :155.0   Median :  0.000   Median :0  
 Mean   :216.1   Mean   :275.4   Mean   :155.4   Mean   :  3.373   Mean   :0  
 3rd Qu.:259.0   3rd Qu.:310.0   3rd Qu.:185.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :469.0   Max.   :332.0   Max.   :128.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :   0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:   0.0000   1st Qu.:39.47   1st Qu.:-4.049   1st Qu.:  42.0  
 Median :   0.0000   Median :41.17   Median :-0.482   Median : 158.0  
 Mean   :   0.0062   Mean   :40.57   Mean   :-1.439   Mean   : 308.7  
 3rd Qu.:   0.0000   3rd Qu.:41.98   3rd Qu.: 1.384   3rd Qu.: 554.0  
 Max.   :1039.0000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip      
 Min.   :  1.0   Min.   :-124.0   Min.   :-157.00   Min.   : 267.0  
 1st Qu.: 90.0   1st Qu.:  98.0   1st Qu.:  45.25   1st Qu.: 353.0  
 Median :217.0   Median : 144.0   Median :  91.00   Median : 415.0  
 Mean   :195.8   Mean   : 141.6   Mean   :  81.23   Mean   : 469.2  
 3rd Qu.:299.0   3rd Qu.: 191.0   3rd Qu.: 128.00   3rd Qu.: 530.0  
 Max.   :366.0   Max.   : 369.0   Max.   : 254.00   Max.   :1206.0  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :  0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0   1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -3.9876  
 Median :0   Median :  0.000   Median :41.96   Median :  0.7789  
 Mean   :0   Mean   :  3.432   Mean   :41.14   Mean   : -1.1966  
 3rd Qu.:0   3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.8375  
 Max.   :0   Max.   :899.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  61.0  
 Median : 287.0  
 Mean   : 659.1  
 3rd Qu.: 900.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin           precip         nevada 
 Min.   : 21.0   Min.   :  7.0   Min.   :-41.0   Min.   :1208   Min.   :0  
 1st Qu.: 80.0   1st Qu.: 80.0   1st Qu.: 47.0   1st Qu.:1300   1st Qu.:0  
 Median :283.0   Median :133.0   Median :102.0   Median :1393   Median :0  
 Mean   :217.2   Mean   :139.1   Mean   : 92.8   Mean   :1518   Mean   :0  
 3rd Qu.:306.0   3rd Qu.:193.0   3rd Qu.:143.0   3rd Qu.:1598   3rd Qu.:0  
 Max.   :354.0   Max.   :282.0   Max.   :202.0   Max.   :3361   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:39.48   1st Qu.: -1.1692   1st Qu.:  43.0  
 Median :  0.000   Median :40.80   Median :  0.4914   Median : 261.0  
 Mean   :  8.256   Mean   :39.53   Mean   : -1.3609   Mean   : 622.9  
 3rd Qu.:  0.000   3rd Qu.:41.84   3rd Qu.:  1.7678   3rd Qu.:1055.0  
 Max.   :559.000   Max.   :43.57   Max.   :  3.0967   Max.   :2519.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax              tmin             precip      
 Min.   :  1.0   Min.   :-196.00   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 91.0   1st Qu.:  30.00   1st Qu.: -31.00   1st Qu.:  0.00  
 Median :184.0   Median :  86.00   Median :  17.00   Median :  0.00  
 Mean   :182.3   Mean   :  87.35   Mean   :  16.08   Mean   : 22.57  
 3rd Qu.:272.0   3rd Qu.: 145.00   3rd Qu.:  68.00   3rd Qu.: 17.00  
 Max.   :366.0   Max.   : 313.00   Max.   : 202.00   Max.   :297.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.78   Min.   :-5.6492  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.363   Mean   :42.24   Mean   : 0.7762  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1199.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   : 823  
 1st Qu.:1894  
 Median :2230  
 Mean   :2127  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  1.0   Min.   :-32.0   Min.   :-75.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:208.0   1st Qu.:145.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :229.1   Mean   :164.5   Mean   :  4.478   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429.0   Max.   :322.0   Max.   :332.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.06   Mean   : 384.3  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin             precip           nevada 
 Min.   :  1.00   Min.   :-61   Min.   :-228.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 36.00   1st Qu.:126   1st Qu.:  25.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 73.00   Median :162   Median :  61.00   Median :  0.00   Median :0  
 Mean   : 84.88   Mean   :160   Mean   :  57.77   Mean   : 26.47   Mean   :0  
 3rd Qu.:112.00   3rd Qu.:194   3rd Qu.:  92.00   3rd Qu.: 17.00   3rd Qu.:0  
 Max.   :366.00   Max.   :389   Max.   : 264.00   Max.   :357.00   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :   0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:   0.0000   1st Qu.:40.30   1st Qu.: -4.767   1st Qu.:  61.0  
 Median :   0.0000   Median :41.43   Median : -1.863   Median : 349.0  
 Mean   :   0.1225   Mean   :40.96   Mean   : -1.968   Mean   : 407.2  
 3rd Qu.:   0.0000   3rd Qu.:42.27   3rd Qu.:  1.165   3rd Qu.: 687.0  
 Max.   :1209.0000   Max.   :43.57   Max.   :  4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  3.0   Min.   :128.0   Min.   : -4.0   Min.   :  0.000   Min.   :0  
 1st Qu.:175.0   1st Qu.:240.0   1st Qu.:126.0   1st Qu.:  0.000   1st Qu.:0  
 Median :217.0   Median :275.0   Median :155.0   Median :  0.000   Median :0  
 Mean   :216.1   Mean   :275.4   Mean   :155.4   Mean   :  3.373   Mean   :0  
 3rd Qu.:259.0   3rd Qu.:310.0   3rd Qu.:185.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :469.0   Max.   :332.0   Max.   :128.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :   0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:   0.0000   1st Qu.:39.47   1st Qu.:-4.049   1st Qu.:  42.0  
 Median :   0.0000   Median :41.17   Median :-0.482   Median : 158.0  
 Mean   :   0.0062   Mean   :40.57   Mean   :-1.439   Mean   : 308.7  
 3rd Qu.:   0.0000   3rd Qu.:41.98   3rd Qu.: 1.384   3rd Qu.: 554.0  
 Max.   :1039.0000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt        tmax             tmin             precip          nevada 
 Min.   :  1   Min.   :-124.0   Min.   :-157.00   Min.   :267.0   Min.   :0  
 1st Qu.: 89   1st Qu.:  98.0   1st Qu.:  45.00   1st Qu.:350.0   1st Qu.:0  
 Median :208   Median : 144.0   Median :  90.00   Median :402.0   Median :0  
 Mean   :194   Mean   : 141.7   Mean   :  80.64   Mean   :433.9   Mean   :0  
 3rd Qu.:299   3rd Qu.: 192.0   3rd Qu.: 128.00   3rd Qu.:494.0   3rd Qu.:0  
 Max.   :366   Max.   : 369.0   Max.   : 254.00   Max.   :763.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -4.0103   1st Qu.:  64.0  
 Median :  0.000   Median :41.98   Median :  0.7433   Median : 316.0  
 Mean   :  3.685   Mean   :41.16   Mean   : -1.2645   Mean   : 659.8  
 3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.8267   3rd Qu.: 897.5  
 Max.   :899.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :  3.0   Min.   :-55.0   Min.   :-92.00   Min.   : 730.0   Min.   :0  
 1st Qu.:110.8   1st Qu.: 98.5   1st Qu.: 50.00   1st Qu.: 803.0   1st Qu.:0  
 Median :271.0   Median :143.0   Median : 97.50   Median : 871.5   Median :0  
 Mean   :218.4   Mean   :140.5   Mean   : 88.44   Mean   : 902.7   Mean   :0  
 3rd Qu.:307.0   3rd Qu.:189.0   3rd Qu.:133.00   3rd Qu.: 984.0   3rd Qu.:0  
 Max.   :362.0   Max.   :321.0   Max.   :240.00   Max.   :1206.0   Max.   :0  
   prof_nieve          longitud        latitud            altitud       
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.00  
 1st Qu.:  0.0000   1st Qu.:40.80   1st Qu.:  0.0714   1st Qu.:  56.75  
 Median :  0.0000   Median :41.60   Median :  1.0544   Median : 252.00  
 Mean   :  0.3125   Mean   :40.84   Mean   : -0.3623   Mean   : 649.78  
 3rd Qu.:  0.0000   3rd Qu.:42.29   3rd Qu.:  2.1553   3rd Qu.: 953.00  
 Max.   :150.0000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.00  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip         nevada 
 Min.   : 21.0   Min.   :  7.0   Min.   :-41.0   Min.   :1208   Min.   :0  
 1st Qu.: 80.0   1st Qu.: 80.0   1st Qu.: 47.0   1st Qu.:1300   1st Qu.:0  
 Median :283.0   Median :133.0   Median :102.0   Median :1393   Median :0  
 Mean   :217.2   Mean   :139.1   Mean   : 92.8   Mean   :1518   Mean   :0  
 3rd Qu.:306.0   3rd Qu.:193.0   3rd Qu.:143.0   3rd Qu.:1598   3rd Qu.:0  
 Max.   :354.0   Max.   :282.0   Max.   :202.0   Max.   :3361   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:39.48   1st Qu.: -1.1692   1st Qu.:  43.0  
 Median :  0.000   Median :40.80   Median :  0.4914   Median : 261.0  
 Mean   :  8.256   Mean   :39.53   Mean   : -1.3609   Mean   : 622.9  
 3rd Qu.:  0.000   3rd Qu.:41.84   3rd Qu.:  1.7678   3rd Qu.:1055.0  
 Max.   :559.000   Max.   :43.57   Max.   :  3.0967   Max.   :2519.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax              tmin             precip      
 Min.   :  1.0   Min.   :-196.00   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 91.0   1st Qu.:  30.00   1st Qu.: -31.00   1st Qu.:  0.00  
 Median :184.0   Median :  86.00   Median :  17.00   Median :  0.00  
 Mean   :182.3   Mean   :  87.35   Mean   :  16.08   Mean   : 22.57  
 3rd Qu.:272.0   3rd Qu.: 145.00   3rd Qu.:  68.00   3rd Qu.: 17.00  
 Max.   :366.0   Max.   : 313.00   Max.   : 202.00   Max.   :297.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.78   Min.   :-5.6492  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.363   Mean   :42.24   Mean   : 0.7762  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1199.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   : 823  
 1st Qu.:1894  
 Median :2230  
 Mean   :2127  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  1.0   Min.   :-32.0   Min.   :-75.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:208.0   1st Qu.:145.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :234.0   Median :172.0   Median :  0.000   Median :0  
 Mean   :180.8   Mean   :229.1   Mean   :164.5   Mean   :  4.478   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:262.0   3rd Qu.:201.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429.0   Max.   :322.0   Max.   :332.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.56   1st Qu.:  25.0  
 Median :0    Median :28.44   Median :-16.33   Median :  33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.06   Mean   : 384.3  
 3rd Qu.:0    3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.:  64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin             precip       
 Min.   :190.0   Min.   :-65.0   Min.   :-240.00   Min.   :  0.000  
 1st Qu.:315.0   1st Qu.:114.0   1st Qu.:  14.00   1st Qu.:  0.000  
 Median :334.0   Median :146.0   Median :  47.00   Median :  0.000  
 Mean   :330.5   Mean   :143.3   Mean   :  44.49   Mean   :  6.211  
 3rd Qu.:350.0   3rd Qu.:175.0   3rd Qu.:  76.00   3rd Qu.:  1.000  
 Max.   :366.0   Max.   :306.0   Max.   : 181.00   Max.   :153.000  
     nevada    prof_nieve          longitud        latitud      
 Min.   :0   Min.   :0.00e+00   Min.   :35.28   Min.   :-8.624  
 1st Qu.:0   1st Qu.:0.00e+00   1st Qu.:40.30   1st Qu.:-4.127  
 Median :0   Median :0.00e+00   Median :41.29   Median :-1.636  
 Mean   :0   Mean   :7.39e-02   Mean   :40.78   Mean   :-1.637  
 3rd Qu.:0   3rd Qu.:0.00e+00   3rd Qu.:42.07   3rd Qu.: 1.331  
 Max.   :0   Max.   :1.24e+03   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 427.0  
 Mean   : 451.1  
 3rd Qu.: 775.0  
 Max.   :1668.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip       
 Min.   :  1.00   Min.   :-61.0   Min.   :-228.00   Min.   :  0.000  
 1st Qu.: 33.00   1st Qu.:128.0   1st Qu.:  21.00   1st Qu.:  0.000  
 Median : 67.00   Median :162.0   Median :  56.00   Median :  0.000  
 Mean   : 70.34   Mean   :159.7   Mean   :  52.49   Mean   :  6.114  
 3rd Qu.:102.00   3rd Qu.:194.0   3rd Qu.:  86.00   3rd Qu.:  2.000  
 Max.   :225.00   Max.   :336.0   Max.   : 190.00   Max.   :136.000  
     nevada    prof_nieve           longitud        latitud      
 Min.   :0   Min.   :   0.0000   Min.   :35.28   Min.   :-8.624  
 1st Qu.:0   1st Qu.:   0.0000   1st Qu.:40.07   1st Qu.:-4.680  
 Median :0   Median :   0.0000   Median :41.38   Median :-1.863  
 Mean   :0   Mean   :   0.1101   Mean   :40.88   Mean   :-1.942  
 3rd Qu.:0   3rd Qu.:   0.0000   3rd Qu.:42.24   3rd Qu.: 1.099  
 Max.   :0   Max.   :1209.0000   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  61.0  
 Median : 353.0  
 Mean   : 412.4  
 3rd Qu.: 690.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  3.0   Min.   :128.0   Min.   : -4.0   Min.   :  0.000   Min.   :0  
 1st Qu.:175.0   1st Qu.:240.0   1st Qu.:126.0   1st Qu.:  0.000   1st Qu.:0  
 Median :217.0   Median :275.0   Median :155.0   Median :  0.000   Median :0  
 Mean   :216.1   Mean   :275.4   Mean   :155.4   Mean   :  3.373   Mean   :0  
 3rd Qu.:259.0   3rd Qu.:310.0   3rd Qu.:185.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :469.0   Max.   :332.0   Max.   :128.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud      
 Min.   :   0.0000   Min.   :35.28   Min.   :-8.624   Min.   :   1.0  
 1st Qu.:   0.0000   1st Qu.:39.47   1st Qu.:-4.049   1st Qu.:  42.0  
 Median :   0.0000   Median :41.17   Median :-0.482   Median : 158.0  
 Mean   :   0.0062   Mean   :40.57   Mean   :-1.439   Mean   : 308.7  
 3rd Qu.:   0.0000   3rd Qu.:41.98   3rd Qu.: 1.384   3rd Qu.: 554.0  
 Max.   :1039.0000   Max.   :43.57   Max.   : 4.216   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip          nevada 
 Min.   :  1.0   Min.   :-31.0   Min.   :-127.00   Min.   : 42.0   Min.   :0  
 1st Qu.: 81.0   1st Qu.:120.0   1st Qu.:  57.00   1st Qu.:102.0   1st Qu.:0  
 Median :145.0   Median :155.0   Median :  90.00   Median :135.0   Median :0  
 Mean   :173.6   Mean   :161.9   Mean   :  89.96   Mean   :150.6   Mean   :0  
 3rd Qu.:288.0   3rd Qu.:199.0   3rd Qu.: 123.00   3rd Qu.:189.0   3rd Qu.:0  
 Max.   :366.0   Max.   :389.0   Max.   : 264.00   Max.   :357.0   Max.   :0  
   prof_nieve           longitud        latitud           altitud    
 Min.   :   0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1  
 1st Qu.:   0.0000   1st Qu.:40.80   1st Qu.: -5.498   1st Qu.:  71  
 Median :   0.0000   Median :41.77   Median : -1.885   Median : 286  
 Mean   :   0.1979   Mean   :41.42   Mean   : -2.127   Mean   : 376  
 3rd Qu.:   0.0000   3rd Qu.:42.59   3rd Qu.:  1.296   3rd Qu.: 617  
 Max.   :1001.0000   Max.   :43.57   Max.   :  4.216   Max.   :1894  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt        tmax             tmin             precip          nevada 
 Min.   :  1   Min.   :-124.0   Min.   :-157.00   Min.   :267.0   Min.   :0  
 1st Qu.: 89   1st Qu.:  98.0   1st Qu.:  45.00   1st Qu.:350.0   1st Qu.:0  
 Median :208   Median : 144.0   Median :  90.00   Median :402.0   Median :0  
 Mean   :194   Mean   : 141.7   Mean   :  80.64   Mean   :433.9   Mean   :0  
 3rd Qu.:299   3rd Qu.: 192.0   3rd Qu.: 128.00   3rd Qu.:494.0   3rd Qu.:0  
 Max.   :366   Max.   : 369.0   Max.   : 254.00   Max.   :763.0   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.87   1st Qu.: -4.0103   1st Qu.:  64.0  
 Median :  0.000   Median :41.98   Median :  0.7433   Median : 316.0  
 Mean   :  3.685   Mean   :41.16   Mean   : -1.2645   Mean   : 659.8  
 3rd Qu.:  0.000   3rd Qu.:42.47   3rd Qu.:  1.8267   3rd Qu.: 897.5  
 Max.   :899.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :  3.0   Min.   :-55.0   Min.   :-92.00   Min.   : 730.0   Min.   :0  
 1st Qu.:110.8   1st Qu.: 98.5   1st Qu.: 50.00   1st Qu.: 803.0   1st Qu.:0  
 Median :271.0   Median :143.0   Median : 97.50   Median : 871.5   Median :0  
 Mean   :218.4   Mean   :140.5   Mean   : 88.44   Mean   : 902.7   Mean   :0  
 3rd Qu.:307.0   3rd Qu.:189.0   3rd Qu.:133.00   3rd Qu.: 984.0   3rd Qu.:0  
 Max.   :362.0   Max.   :321.0   Max.   :240.00   Max.   :1206.0   Max.   :0  
   prof_nieve          longitud        latitud            altitud       
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.00  
 1st Qu.:  0.0000   1st Qu.:40.80   1st Qu.:  0.0714   1st Qu.:  56.75  
 Median :  0.0000   Median :41.60   Median :  1.0544   Median : 252.00  
 Mean   :  0.3125   Mean   :40.84   Mean   : -0.3623   Mean   : 649.78  
 3rd Qu.:  0.0000   3rd Qu.:42.29   3rd Qu.:  2.1553   3rd Qu.: 953.00  
 Max.   :150.0000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.00  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip         nevada 
 Min.   : 21.0   Min.   :  7.0   Min.   :-41.0   Min.   :1208   Min.   :0  
 1st Qu.: 80.0   1st Qu.: 80.0   1st Qu.: 47.0   1st Qu.:1300   1st Qu.:0  
 Median :283.0   Median :133.0   Median :102.0   Median :1393   Median :0  
 Mean   :217.2   Mean   :139.1   Mean   : 92.8   Mean   :1518   Mean   :0  
 3rd Qu.:306.0   3rd Qu.:193.0   3rd Qu.:143.0   3rd Qu.:1598   3rd Qu.:0  
 Max.   :354.0   Max.   :282.0   Max.   :202.0   Max.   :3361   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:39.48   1st Qu.: -1.1692   1st Qu.:  43.0  
 Median :  0.000   Median :40.80   Median :  0.4914   Median : 261.0  
 Mean   :  8.256   Mean   :39.53   Mean   : -1.3609   Mean   : 622.9  
 3rd Qu.:  0.000   3rd Qu.:41.84   3rd Qu.:  1.7678   3rd Qu.:1055.0  
 Max.   :559.000   Max.   :43.57   Max.   :  3.0967   Max.   :2519.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax              tmin             precip      
 Min.   :  1.0   Min.   :-196.00   Min.   :-252.00   Min.   :  0.00  
 1st Qu.: 91.0   1st Qu.:  30.00   1st Qu.: -31.00   1st Qu.:  0.00  
 Median :184.0   Median :  86.00   Median :  17.00   Median :  0.00  
 Mean   :182.3   Mean   :  87.35   Mean   :  16.08   Mean   : 22.57  
 3rd Qu.:272.0   3rd Qu.: 145.00   3rd Qu.:  68.00   3rd Qu.: 17.00  
 Max.   :366.0   Max.   : 313.00   Max.   : 202.00   Max.   :297.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :40.78   Min.   :-5.6492  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:42.18   1st Qu.: 0.7789  
 Median :0   Median :   0.000   Median :42.47   Median : 1.0544  
 Mean   :0   Mean   :   8.363   Mean   :42.24   Mean   : 0.7762  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:42.64   3rd Qu.: 1.7150  
 Max.   :0   Max.   :1199.000   Max.   :42.77   Max.   : 2.4378  
    altitud    
 Min.   : 823  
 1st Qu.:1894  
 Median :2230  
 Mean   :2127  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin            precip            nevada 
 Min.   :  1.0   Min.   :-32.0   Min.   :-75.00   Min.   :  0.000   Min.   :0  
 1st Qu.: 91.0   1st Qu.:101.0   1st Qu.: 27.00   1st Qu.:  0.000   1st Qu.:0  
 Median :180.0   Median :143.0   Median : 65.00   Median :  0.000   Median :0  
 Mean   :181.2   Mean   :144.8   Mean   : 68.34   Mean   :  5.579   Mean   :0  
 3rd Qu.:271.0   3rd Qu.:191.0   3rd Qu.:109.00   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :290.0   Max.   :206.00   Max.   :332.000   Max.   :0  
   prof_nieve    longitud        latitud         altitud    
 Min.   :0    Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.:0    1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median :0    Median :28.31   Median :-16.5   Median :2371  
 Mean   :0    Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.:0    3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :0    Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin             precip       
 Min.   :190.0   Min.   :-65.0   Min.   :-240.00   Min.   :  0.000  
 1st Qu.:315.0   1st Qu.:114.0   1st Qu.:  14.00   1st Qu.:  0.000  
 Median :334.0   Median :146.0   Median :  47.00   Median :  0.000  
 Mean   :330.5   Mean   :143.3   Mean   :  44.49   Mean   :  6.211  
 3rd Qu.:350.0   3rd Qu.:175.0   3rd Qu.:  76.00   3rd Qu.:  1.000  
 Max.   :366.0   Max.   :306.0   Max.   : 181.00   Max.   :153.000  
     nevada    prof_nieve          longitud        latitud      
 Min.   :0   Min.   :0.00e+00   Min.   :35.28   Min.   :-8.624  
 1st Qu.:0   1st Qu.:0.00e+00   1st Qu.:40.30   1st Qu.:-4.127  
 Median :0   Median :0.00e+00   Median :41.29   Median :-1.636  
 Mean   :0   Mean   :7.39e-02   Mean   :40.78   Mean   :-1.637  
 3rd Qu.:0   3rd Qu.:0.00e+00   3rd Qu.:42.07   3rd Qu.: 1.331  
 Max.   :0   Max.   :1.24e+03   Max.   :43.57   Max.   : 4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 427.0  
 Mean   : 451.1  
 3rd Qu.: 775.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :  1.0   Min.   :107.0   Min.   : 38.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 90.0   1st Qu.:216.0   1st Qu.:156.0   1st Qu.:  0.000   1st Qu.:0  
 Median :179.0   Median :239.0   Median :178.0   Median :  0.000   Median :0  
 Mean   :180.7   Mean   :240.5   Mean   :177.5   Mean   :  4.329   Mean   :0  
 3rd Qu.:272.0   3rd Qu.:265.0   3rd Qu.:205.0   3rd Qu.:  0.000   3rd Qu.:0  
 Max.   :366.0   Max.   :429.0   Max.   :322.0   Max.   :318.000   Max.   :0  
   prof_nieve    longitud        latitud          altitud     
 Min.   :0    Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-17.75   1st Qu.: 25.0  
 Median :0    Median :28.46   Median :-16.33   Median : 33.0  
 Mean   :0    Mean   :28.38   Mean   :-16.00   Mean   :114.9  
 3rd Qu.:0    3rd Qu.:28.63   3rd Qu.:-13.86   3rd Qu.: 64.0  
 Max.   :0    Max.   :28.95   Max.   :-13.60   Max.   :632.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)